Cloud feature detection

Abstract

Disclosed is a method and apparatus for detecting cloud features. The method comprises: obtaining image data (e.g. using a camera), the image data defining a plurality of pixels and, for each pixel, a respective luminance value; defining one or more intervals for the luminance values of the pixels; partitioning the image data into one or more image segments ( 502 - 508 ), each respective image segment ( 502 - 508 ) containing pixels having a luminance value in a respective interval; and classifying, as a cloud feature, each image segment ( 502 - 508 ) containing pixels having luminance value greater than or equal to a threshold luminance value (L T ).

The invention claimed is: 
     
       1. A method of detecting cloud features, the method comprising:
 obtaining image data, with one or more cameras, an image, said the image data defining a plurality of pixels and, for each pixel, a respective luminance value; 
 measuring an orientation of the camera when the image was captured; and 
 determining the threshold luminance value (L T ) using the measured orientation 
 defining one or more intervals for the luminance values of the pixels; 
 partitioning the image data into one or more image segments, each respective image segment-containing pixels having a luminance value in a respective interval; and 
 classifying, as a cloud feature, each image segment-containing pixels having luminance value greater than or equal to said threshold luminance value (L T ). 
 
     
     
       2. The method according to  claim 1 , wherein
 obtaining the image data comprises capturing, using one or more cameras, an image; and 
 the method further comprises:
 measuring a time of day at which the camera-captured the image; and 
 determining the threshold luminance value (L T ) using the measured time of day. 
 
 
     
     
       3. The method according to  claim 1 , wherein the step of obtaining image data comprises converting image data into a hue-saturation-luminance coordinate system. 
     
     
       4. The method according to  claim 1 , the method further comprising classifying, as an entity other than a cloud feature, each image segment containing pixels having luminance values less than the threshold luminance value (L T ). 
     
     
       5. The method according to  claim 1 , wherein the step of defining one or more intervals for the luminance values of the pixels comprises:
 determining a maximum of the luminance values of the pixels (L max ); 
 obtaining the threshold luminance value (L T ), the threshold luminance value (L T ) being less than the maximum of the luminance values (L max ); and 
 defining one or more intervals between the maximum of the luminance values (L max ) and the threshold luminance value (L T ). 
 
     
     
       6. The method according to  claim 1 , wherein a size or sizes of the one or more intervals is/are determined using one or more measurements selected from the group of measurements consisting of: a time of day measurement, an orientation measurement, and a measurement of available computational resource. 
     
     
       7. The method according to  claim 1 , wherein
 the step of classifying comprises:
 for a first image segment classified as a cloud feature, assigning a first set of classification labels, the first image segment containing pixels having luminance values in a first interval; 
 for a second image segment classified as a cloud feature, assigning a second set of classification labels, the second image segment containing pixels having luminance values in a second interval, the second interval being different to the first interval, the second set of classification labels being different to the first set of classification labels. 
 
 
     
     
       8. The method according to  claim 7 , wherein:
 the first set of classification labels includes a label indicating a first type of cloud; 
 the second set of classification labels includes a label indicating a second type of cloud, the second type of cloud being different to the first type of cloud. 
 
     
     
       9. The method according to  claim 1 , the method further comprising, for an image segment classified as a cloud feature:
 determining a plurality of moments of that image segment; 
 using the determined plurality of moments, determining a geometric representation of that image segment; and 
 using the geometric representation of that image segment, determining a distance between the cloud feature represented by that image segment and an entity that obtained the image data. 
 
     
     
       10. The method according to  claim 1 , wherein:
 obtaining the image data comprises capturing, using one or more camera, an image-; 
 the camera is mounted on an aircraft; and 
 the method further comprises, controlling the aircraft based on the detected cloud features. 
 
     
     
       11. An apparatus for detecting cloud features, the apparatus comprising:
 one or more sensors-configured to obtain image data, the image data defining a plurality of pixels and, for each pixel, a respective luminance value; 
 one or more processors configured to:
 measure an orientation of the sensors when the image data was captured; and 
 determine a threshold luminance value (L T ) using the measured orientation; 
 define one or more intervals for the luminance values of the pixels; 
 partition the image data into one or more image segments, each respective image segment containing pixels having a luminance value in a respective interval; and 
 classify, as a cloud feature, each image segment containing pixels having luminance value greater than or equal to said threshold luminance value (L T ). 
 
 
     
     
       12. A non-transitory computer readable medium wherein is stored a program or plurality of programs arranged such that when executed by a computer system or one or more processors said program or said plurality of cause the computer system or the one or more processors to operate in accordance with the method of  claim 1 . 
     
     
       13. An aircraft comprising the non-transitory computer readable medium according to  claim 12 .